Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Architectural layout generation using a graph-constrained conditional Generative Adversarial Network (GAN)
https://orcid.org/0000-0001-7273-583X
https://orcid.org/0000-0002-8776-0867
https://orcid.org/0000-0002-4522-5348
Abstract Efficiently generating appealing and realistic architectural space configurations has been a significant challenge for designers. This paper presents a deep-learning approach, providing architects with increased control over the final design outcomes. Employing deep learning algorithms to analyze the graph structure of input bubble diagrams facilitates the generation of node-based space layouts confined within predefined borders, ensuring a balance between creative freedom and practical constraints. The findings reveal the effectiveness of the graph-constrained data-driven method in automating the space layout design process. Automating space arrangement accelerates the building design workflow, yielding more efficient and productive results for architects.
Highlights Data-driven methodologies can automate architectural plan generation. Collaboration between humans and machines can speed up architectural design. To build vectorized space layouts, a pipeline technique is provided. A cGAN algorithm is suggested for producing architectural space layouts. Using CMP technique, the cGAN algorithm operates on the input data’s topology.
Architectural layout generation using a graph-constrained conditional Generative Adversarial Network (GAN)
https://orcid.org/0000-0001-7273-583X
https://orcid.org/0000-0002-8776-0867
https://orcid.org/0000-0002-4522-5348
Abstract Efficiently generating appealing and realistic architectural space configurations has been a significant challenge for designers. This paper presents a deep-learning approach, providing architects with increased control over the final design outcomes. Employing deep learning algorithms to analyze the graph structure of input bubble diagrams facilitates the generation of node-based space layouts confined within predefined borders, ensuring a balance between creative freedom and practical constraints. The findings reveal the effectiveness of the graph-constrained data-driven method in automating the space layout design process. Automating space arrangement accelerates the building design workflow, yielding more efficient and productive results for architects.
Highlights Data-driven methodologies can automate architectural plan generation. Collaboration between humans and machines can speed up architectural design. To build vectorized space layouts, a pipeline technique is provided. A cGAN algorithm is suggested for producing architectural space layouts. Using CMP technique, the cGAN algorithm operates on the input data’s topology.
Architectural layout generation using a graph-constrained conditional Generative Adversarial Network (GAN)
https://orcid.org/0000-0001-7273-583X
https://orcid.org/0000-0002-8776-0867
https://orcid.org/0000-0002-4522-5348
Abstract Efficiently generating appealing and realistic architectural space configurations has been a significant challenge for designers. This paper presents a deep-learning approach, providing architects with increased control over the final design outcomes. Employing deep learning algorithms to analyze the graph structure of input bubble diagrams facilitates the generation of node-based space layouts confined within predefined borders, ensuring a balance between creative freedom and practical constraints. The findings reveal the effectiveness of the graph-constrained data-driven method in automating the space layout design process. Automating space arrangement accelerates the building design workflow, yielding more efficient and productive results for architects.
Highlights Data-driven methodologies can automate architectural plan generation. Collaboration between humans and machines can speed up architectural design. To build vectorized space layouts, a pipeline technique is provided. A cGAN algorithm is suggested for producing architectural space layouts. Using CMP technique, the cGAN algorithm operates on the input data’s topology.
Architectural layout generation using a graph-constrained conditional Generative Adversarial Network (GAN)
Aalaei, Mohammadreza (Autor:in) / Saadi, Melika (Autor:in) / Rahbar, Morteza (Autor:in) / Ekhlassi, Ahmad (Autor:in)
04.08.2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch